Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/iconosquare.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import int_or_none
   5
   6
   7 class IconosquareIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?(?:iconosquare\.com|statigr\.am)/p/(?P<id>[^/]+)'
   9     _TEST = {
  10         'url': 'http://statigr.am/p/522207370455279102_24101272',
  11         'md5': '6eb93b882a3ded7c378ee1d6884b1814',
  12         'info_dict': {
  13             'id': '522207370455279102_24101272',
  14             'ext': 'mp4',
  15             'title': 'Instagram media by @aguynamedpatrick (Patrick Janelle)',
  16             'description': 'md5:644406a9ec27457ed7aa7a9ebcd4ce3d',
  17             'timestamp': 1376471991,
  18             'upload_date': '20130814',
  19             'uploader': 'aguynamedpatrick',
  20             'uploader_id': '24101272',
  21             'comment_count': int,
  22             'like_count': int,
  23         },
  24     }
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28
  29         webpage = self._download_webpage(url, video_id)
  30
  31         media = self._parse_json(
  32             self._search_regex(
  33                 r'window\.media\s*=\s*({.+?});\n', webpage, 'media'),
  34             video_id)
  35
  36         formats = [{
  37             'url': f['url'],
  38             'format_id': format_id,
  39             'width': int_or_none(f.get('width')),
  40             'height': int_or_none(f.get('height'))
  41         } for format_id, f in media['videos'].items()]
  42         self._sort_formats(formats)
  43
  44         title = self._html_search_regex(
  45             r'<title>(.+?)(?: *\(Videos?\))? \| (?:Iconosquare|Statigram)</title>',
  46             webpage, 'title')
  47
  48         timestamp = int_or_none(media.get('created_time') or media.get('caption', {}).get('created_time'))
  49         description = media.get('caption', {}).get('text')
  50
  51         uploader = media.get('user', {}).get('username')
  52         uploader_id = media.get('user', {}).get('id')
  53
  54         comment_count = int_or_none(media.get('comments', {}).get('count'))
  55         like_count = int_or_none(media.get('likes', {}).get('count'))
  56
  57         thumbnails = [{
  58             'url': t['url'],
  59             'id': thumbnail_id,
  60             'width': int_or_none(t.get('width')),
  61             'height': int_or_none(t.get('height'))
  62         } for thumbnail_id, t in media.get('images', {}).items()]
  63
  64         return {
  65             'id': video_id,
  66             'title': title,
  67             'description': description,
  68             'thumbnails': thumbnails,
  69             'timestamp': timestamp,
  70             'uploader': uploader,
  71             'uploader_id': uploader_id,
  72             'comment_count': comment_count,
  73             'like_count': like_count,
  74             'formats': formats,
  75         }